Text Classification
Transformers
Safetensors
Vietnamese
bert
vietnamese
fact-checking
claim-verification
natural-language-inference
vifactcheck
full-context
eacl-2027
Instructions to use BaoNhan/wikibert-ViFactCheck-FC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BaoNhan/wikibert-ViFactCheck-FC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="BaoNhan/wikibert-ViFactCheck-FC")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("BaoNhan/wikibert-ViFactCheck-FC") model = AutoModelForSequenceClassification.from_pretrained("BaoNhan/wikibert-ViFactCheck-FC", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "test_macro_f1_mean": 0.6228599344021635, | |
| "test_macro_f1_std": 0.0013943969424470462, | |
| "test_macro_f1_text": "0.6229 ± 0.0014", | |
| "test_accuracy_mean": 0.6224677716390423, | |
| "test_accuracy_std": 0.002109841480182199, | |
| "test_accuracy_text": "0.6225 ± 0.0021", | |
| "test_macro_precision_mean": 0.6277920951668107, | |
| "test_macro_precision_std": 0.001803497550642567, | |
| "test_macro_precision_text": "0.6278 ± 0.0018", | |
| "test_macro_recall_mean": 0.6216715330235396, | |
| "test_macro_recall_std": 0.0021704411782186074, | |
| "test_macro_recall_text": "0.6217 ± 0.0022", | |
| "dev_macro_f1_mean": 0.612531129450796, | |
| "dev_macro_f1_std": 0.008510090661649844, | |
| "dev_macro_f1_text": "0.6125 ± 0.0085", | |
| "task": "ViFactCheck-full-context", | |
| "dataset": "ViFactCheck", | |
| "model_key": "wikibert", | |
| "model_name": "WikiBERT", | |
| "base_model": "TurkuNLP/wikibert-base-vi-cased", | |
| "seeds": [ | |
| 22, | |
| 42, | |
| 202 | |
| ], | |
| "representative_seed": 42, | |
| "selection_rule": "maximum development Macro-F1; seed ascending tie-break", | |
| "split_policy": "merged_stratified_80_10_10", | |
| "split_seed": 42, | |
| "max_length": 256, | |
| "epochs": 3, | |
| "effective_batch_size": 8 | |
| } |